Research Engineer building post-training, evaluation, and infrastructure for open-weight language models.
Flowers, Movies, Music, and Science. I have an affinity for physics, astronomy, math, and understanding complex systems through the lense of computation. From physical sciences to medicine to cybersecurity to financial markets, I just enjoy working on complex problems, meeting cool people, and storytelling.
Selected work
-
CreSTAL · Post-training research
Built CreSTAL, extending LLMatDesign's crystal-editing workflow with supervised fine-tuning and reinforcement learning from executable feedback. Across four models evaluated on 1,000 held-out materials, RL produced mixed target-hit gains.
Read the case study → -
Atlas · Research infrastructure
A job orchestration layer for post-training research that turns reusable templates into repeatable SLURM training, evaluation, and data-generation workflows.
View the project → -
Cloudflare Radar · 0-to-1 product
Led 0-to-1 product work that turned global network telemetry into a public internet intelligence platform shipped in 12 weeks.
View experience →
Recent writing
-
An application of self-improving harnesses to limit order placement.
#design , #finance , #investment , #agent , #meta
-
A breakdown of an RL environment I designed after misreading a take-home assignment. The design is built around my reverse-engineering background and I liked it enough to write it up here.
-
A LoRA debugging story about four embeddings that never got to learn anything. If you add tokens and freeze the base model, their embedding and LM-head rows still need to train.
#post-training , #sft , #lora , #tokenizers , #ai-assisted
-
Reading GPU telemetry on a colocated GRPO run: periodic utilization dips, memory-access spikes, and a bottleneck story of mine that didn't survive contact with the code.
#rl , #post-training , #grpo , #vllm , #ai-assisted
-
A debugging story about special tokens, GRPO, and the skip_special_tokens flags scattered across your RL stack. When your SFT'd model nails the format in eval, then falls apart the moment it enters the GRPO rollout.
#rl , #post-training , #grpo , #tokenizers , #ai-assisted